A Two-Stage Machine Learning Method To Estimate Stock-Bond Correlation

Accurately estimating the correlation between stocks and bonds is important in effective asset allocation and risk management, which has turned out to be quite challenging due to changing economic conditions. This research addresses these challenges by proposing a new two-stage machine learning methodology to better forecast the complex interplay between stock and bond markets under different economic conditions. In the first stage, the research focuses on the assessment of features across varying economic phases to identify dynamic market risk regimes. After identifying of these regimes, the second stage utilizes supervised machine learning methods to integrate the features to predict stock-bond correlation within each regime. This two-stage approach helps to improve the accuracy of stock-bond correlation forecasting by effectively capturing the dynamics of market risk regimes. It uses these dynamics to help in making precise predictions about factor performance within the respective economic environments.

Author

• Chen, Jiayi

Language

• English

Keyword

• Portfolio Risk Management
• Asset Allocation
• Machine Learning
• Stock-Bond Correlation

Date created

• 2024

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Engineering Management

Degree

• D.Engr.

Advisor

• Ali, Daniyal

Committee Member(s)

• Fong, Titus
• Blackford, Joseph

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/00000077m